Hi @lmweber , thanks for your contribution to nnSVG! I've successfully tested it on my own spatial datasets. However, I'm stuck on the large datasets that have 39000 cells and 26000 genes. I ran >8 hours using spe <- nnSVG(spe, n_threads = 50) on my computer but nnSVG didn't produce the results. How can I improve running efficiency? It seems like the n_threads parameter didn't work after tuning.
Here is my session info.
> sessionInfo()
R version 4.3.0 (2023-04-21 ucrt)
Platform: x86_64-w64-mingw32/x64 (64-bit)
Running under: Windows 10 x64 (build 18363)
Matrix products: default
locale:
[1] LC_COLLATE=Chinese (Simplified)_China.utf8 LC_CTYPE=Chinese (Simplified)_China.utf8
[3] LC_MONETARY=Chinese (Simplified)_China.utf8 LC_NUMERIC=C
[5] LC_TIME=Chinese (Simplified)_China.utf8
time zone: Asia/Shanghai
tzcode source: internal
attached base packages:
[1] stats4 stats graphics grDevices utils datasets methods base
other attached packages:
[1] Matrix_1.6-5 anndata_0.7.5.6 ggplot2_3.5.0
[4] nnSVG_1.6.4 scran_1.30.2 scuttle_1.12.0
[7] SpatialExperiment_1.12.0 SingleCellExperiment_1.24.0 SummarizedExperiment_1.32.0
[10] Biobase_2.62.0 GenomicRanges_1.54.1 MatrixGenerics_1.14.0
[13] matrixStats_1.2.0 dplyr_1.1.4 seqinr_4.2-36
[16] rBLAST_0.99.2 Biostrings_2.70.3 GenomeInfoDb_1.38.8
[19] XVector_0.42.0 IRanges_2.36.0 S4Vectors_0.40.2
[22] BiocGenerics_0.48.1
loaded via a namespace (and not attached):
[1] ade4_1.7-22 tidyselect_1.2.1 BRISC_1.0.5 bitops_1.0-7
[5] RCurl_1.98-1.14 RANN_2.6.1 bluster_1.12.0 rsvd_1.0.5
[9] lifecycle_1.0.4 cluster_2.1.6 statmod_1.5.0 magrittr_2.0.3
[13] compiler_4.3.0 rlang_1.1.3 tools_4.3.0 igraph_2.0.3
[17] utf8_1.2.4 S4Arrays_1.2.1 dqrng_0.3.2 here_1.0.1
[21] reticulate_1.35.0 DelayedArray_0.28.0 rdist_0.0.5 abind_1.4-5
[25] BiocParallel_1.36.0 withr_3.0.0 grid_4.3.0 fansi_1.0.6
[29] beachmat_2.18.1 colorspace_2.1-0 edgeR_4.0.16 scales_1.3.0
[33] MASS_7.3-60.0.1 cli_3.6.2 crayon_1.5.2 generics_0.1.3
[37] metapod_1.10.1 rstudioapi_0.16.0 rjson_0.2.21 DelayedMatrixStats_1.24.0
[41] pbapply_1.7-2 zlibbioc_1.48.2 assertthat_0.2.1 parallel_4.3.0
[45] vctrs_0.6.5 jsonlite_1.8.8 BiocSingular_1.18.0 BiocNeighbors_1.20.2
[49] irlba_2.3.5.1 magick_2.8.3 locfit_1.5-9.9 limma_3.58.1
[53] glue_1.7.0 codetools_0.2-20 gtable_0.3.4 ScaledMatrix_1.10.0
[57] munsell_0.5.1 tibble_3.2.1 pillar_1.9.0 rappdirs_0.3.3
[61] GenomeInfoDbData_1.2.11 R6_2.5.1 sparseMatrixStats_1.14.0 rprojroot_2.0.4
[65] lattice_0.22-6 png_0.1-8 Rcpp_1.0.12 SparseArray_1.2.4
[69] pkgconfig_2.0.3
Hi @lmweber , thanks for your contribution to nnSVG! I've successfully tested it on my own spatial datasets. However, I'm stuck on the large datasets that have 39000 cells and 26000 genes. I ran >8 hours using
spe <- nnSVG(spe, n_threads = 50)on my computer but nnSVG didn't produce the results. How can I improve running efficiency? It seems like then_threadsparameter didn't work after tuning.Here is my session info.